Skip to content

avoid to read whole hive table when spark load from hive table #5047

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
morningman merged 1 commit into from
Dec 15, 2020
Merged

avoid to read whole hive table when spark load from hive table #5047

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 4 additions & 8 deletions fe/spark-dpp/src/main/java/org/apache/doris/load/loadv2/dpp/SparkDpp.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,7 +97,6 @@ public final class SparkDpp implements java.io.Serializable {
private SparkSession spark = null;
private EtlJobConfig etlJobConfig = null;
private LongAccumulator abnormalRowAcc = null;
private LongAccumulator unselectedRowAcc = null;
private LongAccumulator scannedRowsAcc = null;
private LongAccumulator fileNumberAcc = null;
private LongAccumulator fileSizeAcc = null;
Expand All @@ -120,7 +119,6 @@ public SparkDpp(SparkSession spark, EtlJobConfig etlJobConfig) {

public void init() {
abnormalRowAcc = spark.sparkContext().longAccumulator("abnormalRowAcc");
unselectedRowAcc = spark.sparkContext().longAccumulator("unselectedRowAcc");
scannedRowsAcc = spark.sparkContext().longAccumulator("scannedRowsAcc");
fileNumberAcc = spark.sparkContext().longAccumulator("fileNumberAcc");
fileSizeAcc = spark.sparkContext().longAccumulator("fileSizeAcc");
Expand Down Expand Up @@ -854,6 +852,10 @@ private Dataset<Row> loadDataFromHiveTable(SparkSession spark,
sql.append(column.columnName).append(",");
});
sql.deleteCharAt(sql.length() - 1).append(" from ").append(hiveDbTableName);
if (!Strings.isNullOrEmpty(fileGroup.where)) {
sql.append(" where ").append(fileGroup.where);
}

Dataset<Row> dataframe = spark.sql(sql.toString());
dataframe = checkDataFromHiveWithStrictMode(dataframe, baseIndex, fileGroup.columnMappings.keySet(), etlJobConfig.properties.strictMode,
dstTableSchema);
Expand Down Expand Up @@ -988,12 +990,6 @@ private void process() throws Exception {
LOG.info("no data for file file group:" + fileGroup);
continue;
}
if (!Strings.isNullOrEmpty(fileGroup.where)) {
long originalSize = fileGroupDataframe.count();
fileGroupDataframe = fileGroupDataframe.filter(fileGroup.where);
long currentSize = fileGroupDataframe.count();
unselectedRowAcc.add(currentSize - originalSize);
}

JavaPairRDD<List<Object>, Object[]> ret = fillTupleWithPartitionColumn(
fileGroupDataframe,
Expand Down